keel.Algorithms.Instance_Selection.GA_MSE_CC_FSM

Class GA_MSE_CC_FSM

java.lang.Object

keel.Algorithms.Preprocess.Basic.Metodo

keel.Algorithms.Instance_Selection.GA_MSE_CC_FSM.GA_MSE_CC_FSM

public class GA_MSE_CC_FSM
extends Metodo

File: GA_MSE_CC_FSM.java The GA MSE CC FSM Instance Selection algorithm.

Since:

JDK1.5

Version:

0.1

Author:

Written by Salvador García (University of Granada) 20/07/2004

Field Summary

Fields inherited from class keel.Algorithms.Preprocess.Basic.Metodo

clasesTest, clasesTrain, datosTest, datosTrain, distanceEu, entradas, ficheroSalida, ficheroTest, ficheroTraining, ficheroValidation, nEntradas, nominalDistance, nominalTrain, nulosTrain, realTest, realTrain, relation, salida, stdDev, test, training

Constructor Summary

Constructors

Constructor and Description
GA_MSE_CC_FSM(java.lang.String ficheroScript) Default constructor.

Method Summary

Modifier and Type	Method and Description
void	cruceCC(Cromosoma[] poblacion, Cromosoma[] newPob, int nClus, int[] clusters, int size) Computes a new generation of the GA with the clusters given.
void	ejecutar() Executes the algorithm
int[]	kMeans(double[][] datos, int nClus) Execute the kMeans algorithm with the training data given and the number of clusters
void	leerConfiguracion(java.lang.String ficheroScript) Reads the parameters of the algorithm.

Methods inherited from class keel.Algorithms.Preprocess.Basic.Metodo

normalizar

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

GA_MSE_CC_FSM

public GA_MSE_CC_FSM(java.lang.String ficheroScript)

Default constructor. Construct the algoritm by using the superclass builder.

Parameters:

ficheroScript - Configuration script

Method Detail

ejecutar

public void ejecutar()

Executes the algorithm

kMeans

public int[] kMeans(double[][] datos,
                    int nClus)

Execute the kMeans algorithm with the training data given and the number of clusters

Parameters:

datos - dataset in real values.

nClus - number of clusters considered.

Returns:

clusters found.

cruceCC

public void cruceCC(Cromosoma[] poblacion,
                    Cromosoma[] newPob,
                    int nClus,
                    int[] clusters,
                    int size)

Computes a new generation of the GA with the clusters given.

Parameters:

poblacion - actual population.

newPob - new population.

nClus - number of clusters.

clusters - clusters found.

size - size of a chromosome.

leerConfiguracion

public void leerConfiguracion(java.lang.String ficheroScript)

Description copied from class: Metodo

Reads the parameters of the algorithm. Must be implemented in the subclass.

Overrides:

leerConfiguracion in class Metodo

Parameters:

ficheroScript - Configuration script